github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12349] Qwen3-Next #8203

New Issue
Closed
opened 2026-04-12 20:39:55 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-12 20:39:55 -05:00
Owner
Copy Link

Originally created by @chigkim on GitHub (Sep 19, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12349

https://huggingface.co/collections/Qwen/qwen3-next-68c25fd6838e585db8eeea9d?spm=a2ty_o06.30285417.0.0.4766c921yrdQpe

https://qwen.ai/blog?id=4074cca80393150c248e508aa62983f9cb7d27cd&from=research.latest-advancements-list

Thanks!

Originally created by @chigkim on GitHub (Sep 19, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12349 https://huggingface.co/collections/Qwen/qwen3-next-68c25fd6838e585db8eeea9d?spm=a2ty_o06.30285417.0.0.4766c921yrdQpe https://qwen.ai/blog?id=4074cca80393150c248e508aa62983f9cb7d27cd&from=research.latest-advancements-list Thanks!
GiteaMirror added the model label 2026-04-12 20:39:55 -05:00
GiteaMirror commented 2026-04-12 20:39:59 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 19, 2025):

https://github.com/ggml-org/llama.cpp/pull/16095

<!-- gh-comment-id:3314177913 --> @rick-github commented on GitHub (Sep 19, 2025): https://github.com/ggml-org/llama.cpp/pull/16095
GiteaMirror commented 2026-04-12 20:40:00 -05:00
Author
Owner
Copy Link

@timbmg commented on GitHub (Sep 23, 2025):

ggml-org/llama.cpp#16095

Sorry, maybe a dumb question, but do you mean it can only be added once it has been adopted by llama.cpp?

<!-- gh-comment-id:3324143416 --> @timbmg commented on GitHub (Sep 23, 2025): > [ggml-org/llama.cpp#16095](https://github.com/ggml-org/llama.cpp/pull/16095) Sorry, maybe a dumb question, but do you mean it can only be added once it has been adopted by llama.cpp?
GiteaMirror commented 2026-04-12 20:40:01 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 23, 2025):

There's ongoing work to include it in llama.cpp, so it will eventually be available through the old engine.

It's possible that the ollama developers are also working on including it in the new engine (like they did for gpt-oss), but if that work is underway it's not visible through the public repo.

<!-- gh-comment-id:3324162285 --> @rick-github commented on GitHub (Sep 23, 2025): There's ongoing work to include it in llama.cpp, so it will eventually be available through the old engine. It's possible that the ollama developers are also working on including it in the new engine (like they did for gpt-oss), but if that work is underway it's not visible through the public repo.
GiteaMirror commented 2026-04-12 20:40:06 -05:00
Author
Owner
Copy Link

@paolss commented on GitHub (Oct 1, 2025):

this is hard model i can say :) fast good but ... as f hard to implement in vllm llama.cpp etc... ehh.. but worth it

<!-- gh-comment-id:3354310551 --> @paolss commented on GitHub (Oct 1, 2025): this is hard model i can say :) fast good but ... as f hard to implement in vllm llama.cpp etc... ehh.. but worth it
GiteaMirror commented 2026-04-12 20:40:09 -05:00
Author
Owner
Copy Link

@chigkim commented on GitHub (Oct 5, 2025):

It works nicely in MLX.

<!-- gh-comment-id:3369517008 --> @chigkim commented on GitHub (Oct 5, 2025): It works nicely in MLX.
GiteaMirror commented 2026-04-12 20:40:11 -05:00
Author
Owner
Copy Link

@paolss commented on GitHub (Oct 6, 2025):

or in vllm... basically im using it with vllm there is no support for nvidia in lmstudio and ollama - vllm and sglang are working and this model is really good and fast as ...

<!-- gh-comment-id:3369550228 --> @paolss commented on GitHub (Oct 6, 2025): or in vllm... basically im using it with vllm there is no support for nvidia in lmstudio and ollama - vllm and sglang are working and this model is really good and fast as ...
GiteaMirror commented 2026-04-12 20:40:12 -05:00
Author
Owner
Copy Link

@ghecko commented on GitHub (Nov 28, 2025):

Llama.cpp now support it. Any timeframe on when this will be supported by ollama ?

<!-- gh-comment-id:3589600861 --> @ghecko commented on GitHub (Nov 28, 2025): Llama.cpp now support it. Any timeframe on when this will be supported by ollama ?
GiteaMirror commented 2026-04-12 20:40:12 -05:00
Author
Owner
Copy Link

@mehditahmasebi commented on GitHub (Dec 3, 2025):

Qwen3 next 80b 3A is one of the best

<!-- gh-comment-id:3607865249 --> @mehditahmasebi commented on GitHub (Dec 3, 2025): Qwen3 next 80b 3A is one of the best
GiteaMirror commented 2026-04-12 20:40:13 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 3, 2025):

The next vendor sync after b7186 will make support available in ollama.

<!-- gh-comment-id:3607876331 --> @rick-github commented on GitHub (Dec 3, 2025): The next vendor sync after [b7186](https://github.com/ggml-org/llama.cpp/releases/tag/b7186) will make support available in ollama.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label model
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#8203
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?